Deep neural networks are widely deployed in many fields. Due to the in-situ computation (known as processing in memory) capacity of the Resistive Random Access Memory (ReRAM) crossbar, ReRAM-based accelerator shows potential in accelerating DNN with low power and high performance. However, despite power advantage, such kind of accelerators suffer from the high power consumption of peripheral circuits, especially Analog-to-Digital Converter (ADC), which account for over 60 percent of total power consumption. This problem hinders the ReRAM-based accelerator to achieve higher efficiency. Some redundant Analog-to-Digital conversion operations have no contribution to maintaining inference accuracy, and such operations can be eliminated by modifying the ADC searching logic. Based on such observations, we propose an algorithm-hardware co-design method and explore the co-design approach in both hardware design and quantization algorithms. Firstly, we focus on the distribution output along the crossbar's bit-lines and identify the fine-grained redundant ADC sampling bits. % of weight and To further compress ADC bits, we propose a hardware-friendly quantization method and coding scheme, in which different quantization strategy was applied to the partial results in different intervals. To support the two features above, we propose a lightweight architectural design based on SAR-ADC\@. It's worth mentioning that our method is not only more energy efficient but also retains the flexibility of the algorithm. Experiments demonstrate that our method can reduce about $1.6 \sim 2.3 \times$ ADC power reduction.
相關內容
We explore the Ziv-Lempel and Crochemore factorizations of some classical automatic sequences making an extensive use of the theorem prover Walnut.
We formulate a uniform tail bound for empirical processes indexed by a class of functions, in terms of the individual deviations of the functions rather than the worst-case deviation in the considered class. The tail bound is established by introducing an initial "deflation" step to the standard generic chaining argument. The resulting tail bound is the sum of the complexity of the "deflated function class" in terms of a generalization of Talagrand's $\gamma$ functional, and the deviation of the function instance, both of which are formulated based on the natural seminorm induced by the corresponding Cram\'{e}r functions. We also provide certain approximations for the mentioned seminorm when the function class lies in a given (exponential type) Orlicz space, that can be used to make the complexity term and the deviation term more explicit.
We present a novel framework for the development of fourth-order lattice Boltzmann schemes to tackle multidimensional nonlinear systems of conservation laws. Our numerical schemes preserve two fundamental characteristics inherent in classical lattice Boltzmann methods: a local relaxation phase and a transport phase composed of elementary shifts on a Cartesian grid. Achieving fourth-order accuracy is accomplished through the composition of second-order time-symmetric basic schemes utilizing rational weights. This enables the representation of the transport phase in terms of elementary shifts. Introducing local variations in the relaxation parameter during each stage of relaxation ensures the entropic nature of the schemes. This not only enhances stability in the long-time limit but also maintains fourth-order accuracy. To validate our approach, we conduct comprehensive testing on scalar equations and systems in both one and two spatial dimensions.
The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates. This work shows that the classical Adam algorithm is a first order implicit-explicit (IMEX) Euler discretization of the underlying ODE. Employing the time discretization point of view, we propose new extensions of the Adam scheme obtained by using higher order IMEX methods to solve the ODE. Based on this approach, we derive a new optimization algorithm for neural network training that performs better than classical Adam on several regression and classification problems.
Detecting polyps through colonoscopy is an important task in medical image segmentation, which provides significant assistance and reference value for clinical surgery. However, accurate segmentation of polyps is a challenging task due to two main reasons. Firstly, polyps exhibit various shapes and colors. Secondly, the boundaries between polyps and their normal surroundings are often unclear. Additionally, significant differences between different datasets lead to limited generalization capabilities of existing methods. To address these issues, we propose a segmentation model based on Prompt-Mamba, which incorporates the latest Vision-Mamba and prompt technologies. Compared to previous models trained on the same dataset, our model not only maintains high segmentation accuracy on the validation part of the same dataset but also demonstrates superior accuracy on unseen datasets, exhibiting excellent generalization capabilities. Notably, we are the first to apply the Vision-Mamba architecture to polyp segmentation and the first to utilize prompt technology in a polyp segmentation model. Our model efficiently accomplishes segmentation tasks, surpassing previous state-of-the-art methods by an average of 5% across six datasets. Furthermore, we have developed multiple versions of our model with scaled parameter counts, achieving better performance than previous models even with fewer parameters. Our code and trained weights will be released soon.
Multiple-conclusion Hilbert-style systems allow us to finitely axiomatize every logic defined by a finite matrix. Having obtained such axiomatizations for Paraconsistent Weak Kleene and Bochvar-Kleene logics, we modify them by replacing the multiple-conclusion rules with carefully selected single-conclusion ones. In this way we manage to introduce the first finite Hilbert-style single-conclusion axiomatizations for these logics.
Lattices are architected metamaterials whose properties strongly depend on their geometrical design. The analogy between lattices and graphs enables the use of graph neural networks (GNNs) as a faster surrogate model compared to traditional methods such as finite element modelling. In this work, we generate a big dataset of structure-property relationships for strut-based lattices. The dataset is made available to the community which can fuel the development of methods anchored in physical principles for the fitting of fourth-order tensors. In addition, we present a higher-order GNN model trained on this dataset. The key features of the model are (i) SE(3) equivariance, and (ii) consistency with the thermodynamic law of conservation of energy. We compare the model to non-equivariant models based on a number of error metrics and demonstrate its benefits in terms of predictive performance and reduced training requirements. Finally, we demonstrate an example application of the model to an architected material design task. The methods which we developed are applicable to fourth-order tensors beyond elasticity such as piezo-optical tensor etc.
Regent is an implicitly parallel programming language that allows the development of a single codebase for heterogeneous platforms targeting CPUs and GPUs. This paper presents the development of a parallel meshfree solver in Regent for two-dimensional inviscid compressible flows. The meshfree solver is based on the least squares kinetic upwind method. Example codes are presented to show the difference between the Regent and CUDA-C implementations of the meshfree solver on a GPU node. For CPU parallel computations, details are presented on how the data communication and synchronisation are handled by Regent and Fortran+MPI codes. The Regent solver is verified by applying it to the standard test cases for inviscid flows. Benchmark simulations are performed on coarse to very fine point distributions to assess the solver's performance. The computational efficiency of the Regent solver on an A100 GPU is compared with an equivalent meshfree solver written in CUDA-C. The codes are then profiled to investigate the differences in their performance. The performance of the Regent solver on CPU cores is compared with an equivalent explicitly parallel Fortran meshfree solver based on MPI. Scalability results are shown to offer insights into performance.
Shared control can ease and enhance a human operator's ability to teleoperate robots, particularly for intricate tasks demanding fine control over multiple degrees of freedom. However, the arbitration process dictating how much autonomous assistance to administer in shared control can confuse novice operators and impede their understanding of the robot's behavior. To overcome these adverse side-effects, we propose a novel formulation of shared control that enables operators to tailor the arbitration to their unique capabilities and preferences. Unlike prior approaches to customizable shared control where users could indirectly modify the latent parameters of the arbitration function by issuing a feedback command, we instead make these parameters observable and directly editable via a virtual reality (VR) interface. We present our user-customizable shared control method for a teleoperation task in SE(3), known as the buzz wire game. A user study is conducted with participants teleoperating a robotic arm in VR to complete the game. The experiment spanned two weeks per subject to investigate longitudinal trends. Our findings reveal that users allowed to interactively tune the arbitration parameters across trials generalize well to adaptations in the task, exhibiting improvements in precision and fluency over direct teleoperation and conventional shared control.
Knowledge graphs capture structured information and relations between a set of entities or items. As such they represent an attractive source of information that could help improve recommender systems. However existing approaches in this domain rely on manual feature engineering and do not allow for end-to-end training. Here we propose knowledge-aware graph neural networks with label smoothness regularization to provide better recommendations. Conceptually, our approach computes user-specific item embeddings by first applying a trainable function that identifies important knowledge graph relationships for a given user. This way we transform the knowledge graph into a user-specific weighted graph and then applies a graph neural network to compute personalized item embeddings. To provide better inductive bias, we use label smoothness, which assumes that adjacent items in the knowledge graph are likely to have similar user relevance labels/scores. Label smoothness provides regularization over edge weights and we prove that it is equivalent to a label propagation scheme on a graph. Finally, we combine knowledge-aware graph neural networks and label smoothness and present the unified model. Experiment results show that our method outperforms strong baselines in four datasets. It also achieves strong performance in the scenario where user-item interactions are sparse.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191